mlsanityData to 14 Oct 2026

AI-Enabled grading with near-domain data for scaling feedback with human-level accuracy

arXiv 2512.04113 ↗First posted 1 Dec 2025cs.CY cs.AI cs.HCcited by 0

Not on the map. Why?

Abstract (arXiv)

Constructed-response questions are crucial to encourage generative processing and test a learner's understanding of core concepts. However, the limited availability of instructor time, large class sizes, and other resource constraints pose significant challenges in providing timely and detailed evaluation, which is crucial for a holistic educational experience. In addition, providing timely and frequent assessments is challenging since manual grading is labor intensive, and automated grading is complex to generalize to every possible response scenario. This paper proposes a novel and practical approach to grade short-answer constructed-response questions. We discuss why this problem is challenging, define the nature of questions on which our method works, and finally propose a framework that instructors can use to evaluate their students' open-responses, utilizing near-domain data like data from similar questions administered in previous years. The proposed method outperforms the state of the art machine learning models as well as non-fine-tuned large language models like GPT 3.5, GPT 4, and GPT 4o by a considerable margin of over 10-20% in some cases, even after providing the LLMs with reference/model answers. Our framework does not require pre-written grading rubrics and is designed explicitly with practical classroom settings in mind. Our results also reveal exciting insights about learning from near-domain data, including what we term as accuracy and data advantages using human-labeled data, and we believe this is the first work to formalize the problem of automated short answer grading based on the near-domain data.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 62 references that are in the map. First posted on arXiv 1 Dec 2025.

Builds on

17 of 62 references.

References · 17

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2022Training language models to follow instructions with human feedbackcited by 15,971
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  6. 2020GLU Variants Improve Transformercited by 1,804
  7. 2023Whose Opinions Do Language Models Reflect?cited by 773
  8. 2024A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Sciencecited by 31
  9. 2023Towards LLM-based Autograding for Short Textual Answerscited by 20
  10. 2018Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inferencecited by 16
  11. 2023Performance of the Pre-Trained Large Language Model GPT-4 on Automated Short Answer Gradingcited by 15
  12. 2019Automatic Short Answer Grading via Multiway Attention Networkscited by 8
5 more
  1. 2023Short Answer Grading Using One-shot Prompting and Text Similarity Scoring Modelcited by 7
  2. 2024Grading Massive Open Online Courses Using Large Language Modelscited by 7
  3. 2020Comparative Evaluation of Pretrained Transfer Learning Models on Automatic Short Answer Gradingcited by 5
  4. 2023Can LLMs Grade Short-Answer Reading Comprehension Questions : An Empirical Study with a Novel Datasetcited by 4
  5. 2025The Hidden AI Race: Tracking Environmental Costs of Innovationcited by 1

Built on by

Not cited yet.